Breeding farm cattle and sheep brucellosis prevention and control and intelligent early warning system

Abstract

The invention discloses a brucellosis prevention and control and intelligent early warning system for cattle and sheep groups in a livestock farm, relates to the technical field of brucellosis prevention and control, overcomes the hysteresis problem of a traditional brucellosis prevention and control method in the livestock farm through real-time data acquisition and dynamic monitoring, and can discover and take measures in time in the early stage of epidemic disease occurrence so as to prevent and control the brucellosis. Therefore, the risk of epidemic situation spreading is effectively reduced. An artificial intelligence three-layer neural network model is used for accurate prediction of brucellosis infection risks, uncertainty in traditional experience judgment is avoided, and prevention and control measures are more scientific and reasonable. According to the method, comprehensive evaluation is carried out by combining the individual antibody level and population immune data, the immune strategy can be adjusted in time according to the actual situation, the immune effect and the coverage rate are improved, immune blind areas are avoided, and the maximum effect of immune measures is ensured. The monitoring and troubleshooting module generates a personalized action scheme according to different risk levels, so that the blindness of'one-step cutting 'in a traditional method is effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of brucellosis prevention and control, and specifically to a brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm. Background Art

[0002] With the global emphasis on food safety, the prevention and control of animal diseases, especially infectious diseases, has gradually become an important task for all types of farms. Brucellosis, as a widespread zoonosis, has become a difficult problem that needs to be solved in the global livestock health management. Brucellosis not only affects the growth and reproduction of cattle and sheep, but can also be transmitted to humans, posing a public health risk. Therefore, how to accurately monitor, timely predict and effectively prevent and control brucellosis through scientific and technological means is an urgent challenge facing the current cattle and sheep breeding industry.

[0003] At present, although major farms have adopted some traditional brucellosis prevention and control measures, such as regular vaccination and antibody testing, these methods have significant deficiencies in dealing with brucellosis prevention and control due to the lack of real-time monitoring and dynamic risk assessment. Traditional methods usually rely on manual sampling and periodic testing, resulting in information lag and failure to timely discover potential risk sources. At the same time, the occurrence of brucellosis is often closely related to environmental factors, personnel flow and other data.

[0004] The information lag and insufficiency in the existing prevention and control system may result in the brucellosis epidemic not being discovered and controlled in time in the early stages, and comprehensive immunization measures or large-scale culling are not initiated until the infection becomes serious. This not only causes direct economic losses to farms, but also poses a potential threat to public health. Specifically, infected individuals in cattle and sheep herds that are not isolated or eliminated in time may inadvertently spread the pathogen, causing the epidemic to spread and affect a wider range of areas and other animal populations. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a brucellosis prevention and control and intelligent early warning system for cattle and sheep in a farm, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a brucellosis prevention and control and intelligent early warning system for cattle and sheep in breeding farms, including a data acquisition module, a data processing module, an AI risk prediction module, a monitoring and investigation module, an immune effect evaluation module and an intelligent early warning and feedback module;

[0007] The data acquisition module collects real-time data and historical data, including environmental parameters, cattle and sheep health data, and human and logistics data, and establishes a data pool X;

[0008] The data processing module standardizes and classifies the data pool X, and calculates core indicators, including the environmental risk score Re, the cattle and sheep health score Hs, and the human and logistics risk score Cr;

[0009] The AI ​​risk prediction module predicts the risk of brucellosis infection based on the core indicators by using a three-layer neural network model to obtain the brucellosis infection risk probability Pr and risk level;

[0010] The monitoring and screening module generates a specific action plan based on the brucellosis infection risk probability Pr and risk level, and detects the average antibody level Am and the antibody qualification rate Ra to obtain the individual antibody level AQ;

[0011] The immune effect evaluation module evaluates the vaccine effect and immune coverage rate FRA through the individual antibody level AQ and the average antibody level Am, and modifies the immune strategy;

[0012] The intelligent early warning and feedback module feeds back the brucellosis infection risk probability Pr and the average antibody level Am to the manager and generates adjustment suggestions.

[0013] Preferably, the data collection module includes an environmental data collection unit, a cattle and sheep health data collection unit, and a human and logistics data collection unit;

[0014] The environmental data acquisition unit collects environmental parameters related to the spread of brucellosis, including temperature T, humidity H and air circulation rate F; the temperature T and humidity H are obtained by temperature sensors and humidity sensors installed in the farm, and the air circulation rate F is obtained by wind speed sensors;

[0015] The cattle and sheep health data collection unit collects cattle and sheep health data, including historical antibody levels Ah and abortion rates Lr; the historical antibody levels Ah are obtained by regularly collecting cattle and sheep serum samples every month and testing them in the laboratory; the abortion rate Lr is automatically calculated and obtained by recording the frequency of abortion events in cattle and sheep in the past year through the management system;

[0016] The abortion rate Lr is obtained by the ratio of the number of aborted individuals in one year to the total number of pregnant individuals in the group;

[0017] The personnel and logistics data collection unit monitors data related to outside personnel and logistics, including the personnel contact frequency Cp and the number of outside cattle and sheep In; the personnel contact frequency Cp is obtained through the access control system and the electronic sign-in record; the number of outside cattle and sheep In is obtained by recording the number of cattle and sheep transferred into the farm, and the environmental parameters, cattle and sheep health data and personnel and logistics data are summarized and fitted into a data pool X.

[0018] Preferably, the data processing module includes a data standardization unit and a core indicator calculation unit;

[0019] The standardization unit normalizes the data in the data pool X to eliminate the influence of different parameter dimensions and obtains the data set W;

[0020] The data set W is obtained by the following formula:

[0021]

[0022] Where Wi represents the data value of the i-th item in the data set W, Xi represents the data value of the i-th item in the data pool X, Xi,min represents the valley value of the data value of the i-th item in the data pool X, and Xi,max represents the peak value of the data value of the i-th item in the data pool X;

[0023] The core indicator calculation unit calculates the core indicators based on the standardized data set W, including the environmental risk score Re, the cattle and sheep health score Hs, and the human flow and logistics risk score Cr;

[0024] The environmental risk score Re is obtained by the following formula:

[0025]

[0026] In the formula, ln represents the natural logarithm function;

[0027] The cattle and sheep health score Hs is obtained by the following formula:

[0028]

[0029] Where e -Ah represents the exponential decay effect of antibody levels;

[0030] The personnel and logistics risk score Cr is obtained by the following formula:

[0031]

[0032] Where ln represents the natural logarithmic function. ln(1+Cp*In) represents the coupling risk of human flow and logistics.

[0033] Preferably, the AI ​​risk prediction module includes a data input and preprocessing unit and a risk prediction and output unit;

[0034] The data input and preprocessing unit performs feature combination and normalization processing on the received environmental risk score Re, cattle and sheep health score Hs and human flow and logistics risk score Cr to obtain a feature set Y = {L1, L2, L3};

[0035] In the formula, L1 represents the relative impact of comprehensive assessment of environmental risk and health status, while considering the adjustment effect of logistics risk; L2 represents the weighted cumulative effect of core indicators, taking the natural logarithm to smooth the data distribution; L3 represents the square accumulation of environmental and health scores, balancing the excessive impact of high-value indicators on the prediction results;

[0036] The relative impact L1 of the comprehensive assessment of environmental risks and health conditions is obtained by the following formula:

[0037]

[0038] The weighted cumulative effect L2 of the core indicators is obtained by the following formula:

[0039] L2=ln(1+Re+Hs+Cr);

[0040] In the formula, ln represents the natural logarithm function;

[0041] The square accumulation L3 of the environmental and health scores is obtained by the following formula:

[0042]

[0043] The relative impact L1 of the comprehensive assessment of environmental risks and health conditions, the weighted cumulative effect L2 of the core indicators and the square accumulation L3 of the environmental and health scores were normalized to obtain the feature set Y = {L1, L2, L3}.

[0044] Preferably, the risk prediction and output unit trains and predicts the input feature set Y by using a three-layer neural network model, and outputs the brucellosis infection risk probability Pr and the corresponding risk level;

[0045] Specifically, the brucellosis infection risk probability Pr is obtained through the first output layer Z1 and the second output layer Z2 of the three-layer neural network model;

[0046] The first output layer Z1 and the second output layer Z2 are obtained by the following formula:

[0047] Z1=σ(V1*Y+b1);

[0048] Z2=σ(V2*Z1+b2);

[0049] Where σ represents the Sigmoid activation function, b1 and b2 represent bias vectors, and V1 and V2 represent weight matrices;

[0050] The brucellosis infection risk probability Pr is obtained by the following formula:

[0051] Pr=σ(V3*Z2+b3);

[0052] Where b3 represents the bias vector and V3 represents the weight matrix;

[0053] According to the obtained brucellosis infection risk probability Pr, the corresponding risk level is divided;

[0054] The risk level is obtained by matching:

[0055] When the brucellosis infection risk probability Pr is less than 0.3, it is marked as the first risk level and monitored normally;

[0056] When 0.3≤brucellosis infection risk probability Pr≤0.7, it is marked as the second risk level and is monitored intensively;

[0057] When the brucellosis infection risk probability Pr>0.7, it is marked as the third risk level and control measures are taken.

[0058] Preferably, the monitoring and troubleshooting module includes an action plan generation unit and an antibody level detection unit;

[0059] The action plan generating unit generates an action plan according to the brucellosis infection risk probability Pr and the risk level, including a screening range NS, a detection frequency FD and an isolation strategy NI;

[0060] The screening range NS is obtained by the following formula:

[0061] NS = Pr * Nt;

[0062] In the formula, Nt represents the total number of cattle and sheep in the farm;

[0063] The detection frequency FD is obtained by the following formula:

[0064]

[0065] The probability of brucellosis infection risk Pr is graded according to 0.2, with the first risk level being once a month, the second risk level being 3 times a month, and the third risk level being 5 times a month;

[0066] The isolation strategy NI is obtained by the following formula:

[0067]

[0068] In the formula, Ir represents the proportion of positive individuals found in the test, and Dr represents the detection accuracy error coefficient.

[0069] Screening scope NS: tells managers the number of cattle and sheep that need to be tested;

[0070] Testing frequency FD: Determine the testing plan cycle to ensure early detection of risks;

[0071] Isolation scope NI: Guide managers to quickly isolate potentially high-risk individuals and cut off the chain of transmission.

[0072] Preferably, the antibody level detection unit collects blood samples from the screened individuals, detects the average antibody level Am and the antibody qualification rate Ra, obtains the individual antibody level AQ, compares it with the preset immune threshold Ta, and determines the immune status of the cattle and sheep individuals:

[0073] The average antibody level Am is obtained by the following formula:

[0074]

[0075] In the formula, ATi represents the antibody value of the i-th cattle and sheep, obtained by serological testing, and n represents the total number of individuals tested;

[0076] The antibody qualified rate Ra is obtained by the ratio of the number of individuals with antibody levels higher than the average antibody level Am to the total number of tested individuals n;

[0077] The individual antibody level AQ is obtained by the following formula:

[0078]

[0079] In the formula, Na represents the number of individuals with qualified antibodies, specifically the number of individuals with antibody levels higher than the average antibody level Am, and ln represents the natural logarithm function;

[0080] The immune status of the cattle and sheep individuals is obtained by matching in the following manner:

[0081] When the individual antibody level AQ is less than the immune threshold Ta, it means that the individual antibody level does not meet the standard and is listed as a key observation object;

[0082] When the individual antibody level AQ ≥ the immune threshold Ta, it means that the individual antibody level has reached the standard and monitoring should continue.

[0083] Preferably, the immune effect evaluation module includes an immune evaluation unit and an immune strategy correction unit;

[0084] The immune assessment unit obtains the population antibody mean deviation value ΔAm based on the average antibody level Am, and determines the immune effect:

[0085] The population antibody mean deviation ΔAm is obtained by the following formula:

[0086] ΔAm=Am-Ta;

[0087] The immune effect is obtained by:

[0088] When the population antibody mean deviation value ΔAm>0, it means that the vaccine effect meets expectations;

[0089] When the population antibody mean deviation ΔAm is less than 0, it means that the vaccine effect does not meet expectations and the immunization strategy should be revised;

[0090] Through the individual antibody level AQ, the immune coverage rate FRA is obtained and the immune coverage efficiency is judged:

[0091] The immunization coverage rate FRA is obtained by the following formula:

[0092]

[0093] The immune coverage efficiency is obtained by:

[0094] When the immunization coverage rate FRA is less than 85%, it means that the immunization coverage does not meet the standard and there is a blind spot, so the immunization strategy should be revised;

[0095] When the immunization coverage rate FRA ≥ 85%, it means that the immunization coverage has met the standard.

[0096] Preferably, the immunization strategy modification unit obtains the immune reinforcement area according to the vaccine effect and the immunization coverage rate FRA, and modifies the immunization strategy, including vaccine dosage adjustment and immunization frequency adjustment;

[0097] The immune enhancement area is obtained by:

[0098]

[0099] In the formula, Rf represents the set of individuals that need immune enhancement, including individuals with low antibody levels and insufficient contribution to group immunity, which are the main source of obtaining immune enhancement areas, and Gi represents the individual immunity contribution rate;

[0100] The vaccine dose adjustment formula is as follows:

[0101]

[0102] In the formula, Dv represents the vaccine dose required for booster immunization, Db represents the basic immunization dose; Ta-AQ represents the immunity gap, which is used to dynamically adjust the dose.

[0103] The immunization frequency adjustment formula is as follows:

[0104]

[0105] Where Ra represents the antibody qualification rate. 1 / Ra represents the inverse ratio of the antibody qualification rate, which is used for frequency adjustment of high-risk groups.

[0106] Preferably, the intelligent early warning and feedback module includes a risk early warning unit and an adjustment suggestion generating unit;

[0107] The risk warning unit calculates and obtains the comprehensive immune status score Sc according to the brucellosis infection risk probability Pr and the average antibody level Am;

[0108] The comprehensive immune status score Sc is obtained by the following formula:

[0109]

[0110] The adjustment suggestion generating unit generates a management adjustment suggestion AG according to the comprehensive immune status score Sc;

[0111] The adjustment suggestion AG obtains the following methods:

[0112]

[0113] The present invention provides a brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm, which has the following beneficial effects:

[0114] (1) When the system is running, through real-time data collection and dynamic monitoring, it overcomes the lag problem of traditional brucellosis prevention and control methods in farms, and can promptly detect and take measures in the early stages of the disease, thereby effectively reducing the risk of the spread of the epidemic. The use of an artificial intelligence three-layer neural network model to accurately predict the risk of brucellosis infection avoids the uncertainty in traditional empirical judgments, making prevention and control measures more scientific and reasonable, and reducing the possibility of human errors or omissions.

[0115] The present invention combines individual antibody levels with group immunity data for comprehensive evaluation, and can timely adjust the immunization strategy according to actual conditions, improve the immunization effect and coverage, avoid the occurrence of immunization blind spots, and ensure the maximum effect of immunization measures. The monitoring and investigation module effectively avoids the blindness of the "one-size-fits-all" approach in traditional methods by generating personalized action plans according to different risk levels, making prevention and control measures more accurate, thereby improving the pertinence and effectiveness of brucellosis prevention and control. The intelligent feedback mechanism of the intelligent early warning and feedback module can provide managers with timely decision-making support, ensuring that scientific and reasonable responses can be made before or in the early stages of an epidemic, reducing the problem of epidemic spread caused by information delays or decision lags.

[0116] (2) Through the comprehensive collection of three major types of data, namely, environment, cattle and sheep health, and human and logistics, the limitations of the single data source of traditional prevention and control methods have been overcome, and various risk factors for the spread of brucellosis can be comprehensively evaluated. The multi-dimensional collection of data has improved the accuracy and comprehensiveness of brucellosis prevention and control. The introduction of data standardization processing units and core indicator calculation units ensures the uniformity and accuracy of different types of data and realizes automated data analysis. This automated processing not only greatly improves work efficiency, but also reduces errors in human operations, ensuring the scientific nature of prevention and control decisions.

[0117] By dynamically calculating environmental risks, cattle and sheep health risks, and human and logistics risk scores, the system can reflect the potential threat of brucellosis in real time and accurately. Compared with the traditional static assessment method, the dynamic risk assessment of this embodiment can be adjusted in time with environmental changes and epidemic spread trends, so that brucellosis prevention and control measures can respond to new challenges at any time. The collection and analysis of cattle and sheep health data provides a scientific basis for the evaluation of immune effects. Through real-time monitoring of key health indicators such as abortion rate and antibody levels, the system can help evaluate the effectiveness of vaccination and promptly discover blind spots in immune coverage, thereby maximizing the immune effect and ensuring the success of purifying brucellosis.

[0118] (3) Through a comprehensive assessment of the three major factors of environment, health, and human and logistics, the system can comprehensively consider the risk of brucellosis transmission in multiple dimensions. This comprehensiveness ensures that the evaluation results will not be limited by a single factor, and can more accurately predict the risk of brucellosis infection and provide managers with more scientific prevention and control recommendations. The use of deep neural network models for risk prediction gives the system the ability to adaptively learn. Over time, the system can continuously acquire new knowledge from new data and automatically adjust the prediction model to cope with different farm environments and dynamically changing epidemic risks. This intelligent model improves the long-term stability and accuracy of the system.

[0119] By calculating the infection risk probability Pr, the system can classify brucellosis risks into three levels: normal monitoring, key monitoring and control measures. This probability-based classification method enables managers to take more targeted prevention and control measures, flexibly adjust monitoring and management strategies according to actual conditions, avoid waste of resources and efficiently control the epidemic.

[0120] The system's automated risk prediction and early warning functions can provide timely feedback to managers when infection risks change, allowing them to quickly adjust response strategies. Compared with manual judgment, the automated system's response speed and accuracy are significantly improved, ensuring that managers can take the most effective prevention and control measures at the first opportunity. The risk prediction module not only predicts the probability of infection, but also conducts a comprehensive assessment of risks based on specific environmental, health, and logistics data. This allows for more accurate location of risk sources and potential outbreak points, allowing for targeted immunization, isolation, disinfection, and other measures to maximize prevention and control effects and reduce the spread and impact of brucellosis.

[0121] (4) By combining infection risk prediction and antibody level monitoring, the system can accurately formulate and dynamically adjust prevention and control plans. This intelligent and flexible prevention and control strategy can adjust the screening scope, detection frequency and isolation strategy according to actual conditions, avoiding blind prevention and control and waste of resources, and improving the prevention and control effect. The system accurately calculates the antibody level and antibody qualification rate, and compares them with the immune threshold to intelligently judge the individual's immune status. This not only makes the immune effect evaluation more scientific and comprehensive, but also can take further measures for individuals who do not meet the immune standards to ensure that there are no blind spots in the immune purification of brucellosis. The system has real-time feedback and dynamic optimization capabilities, and can intelligently adjust the immune and monitoring strategies according to the changes in detection data and antibody levels. This flexible adjustment mechanism greatly improves the response speed and accuracy of the prevention and control strategy, thereby enhancing the timeliness and effectiveness of brucellosis prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0122] Figure 1 The present invention is a schematic diagram of the flowchart of a brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm. DETAILED DESCRIPTION

[0123] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0124] Example 1

[0125] The present invention provides a brucellosis prevention and control and intelligent early warning system for cattle and sheep in breeding farms. Figure 1 , including data collection module, data processing module, AI risk prediction module, monitoring and investigation module, immune effect evaluation module and intelligent early warning and feedback module;

[0126] The data acquisition module collects real-time data and historical data, including environmental parameters, cattle and sheep health data, and human and logistics data, and establishes a data pool X;

[0127] The data processing module standardizes and classifies the data pool X, and calculates core indicators, including the environmental risk score Re, the cattle and sheep health score Hs, and the human and logistics risk score Cr;

[0128] The AI ​​risk prediction module predicts the risk of brucellosis infection based on the core indicators by using a three-layer neural network model to obtain the brucellosis infection risk probability Pr and risk level;

[0129] The monitoring and screening module generates a specific action plan based on the brucellosis infection risk probability Pr and risk level, and detects the average antibody level Am and the antibody qualification rate Ra to obtain the individual antibody level AQ;

[0130] The immune effect evaluation module evaluates the vaccine effect and immune coverage rate FRA through the individual antibody level AQ and the average antibody level Am, and modifies the immune strategy;

[0131] The intelligent early warning and feedback module feeds back the brucellosis infection risk probability Pr and the average antibody level Am to the manager and generates adjustment suggestions.

[0132] In this embodiment, through the real-time monitoring and historical data collection of the environment, cattle and sheep health data, and human and logistics by the data acquisition module, the system can obtain various dynamic information in the farm in a timely manner. Unlike the traditional regular detection method, this real-time data collection mode can achieve early warning, so that the risk of brucellosis can be identified and dealt with in the first time, greatly improving the prevention efficiency and response speed. Using the AI ​​risk prediction module, combined with the environmental risk score, cattle and sheep health score, and human and logistics risk score, a three-layer neural network model is used to accurately predict the risk of brucellosis infection. This risk prediction based on artificial intelligence not only takes into account historical data, but also dynamically adjusts the assessment of the current risk situation, thereby avoiding the lag and singleness of traditional methods, providing farms with more accurate and scientific risk assessments, and reducing the potential risk of epidemic outbreaks.

[0133] The immune effect evaluation module conducts a comprehensive evaluation of the immune effect based on the individual antibody level and the average antibody level of the group, and promptly amends the immune strategy. This function can help farms discover immune blind spots and individuals with substandard antibody levels, so as to timely adjust immune measures during the brucellosis purification process to ensure the maximization of immune effects and improve the prevention and control effects. According to the infection risk probability and risk level provided by the AI ​​risk prediction module, the monitoring and investigation module can automatically generate customized action plans. Through targeted immune screening of cattle and sheep, antibody level testing, etc., positive individuals are eliminated in a timely manner, effectively reducing the possibility of disease transmission. This customized action plan ensures the accuracy of prevention and control measures, avoids the one-size-fits-all approach in traditional methods, and improves the efficiency of epidemic prevention.

[0134] The intelligent early warning and feedback module can provide managers with real-time feedback on information such as the probability of brucellosis infection risk and antibody levels, and generate adjustment suggestions. This function not only improves managers' decision-making ability, but also allows them to respond in a timely manner, avoiding the risk of epidemic spread caused by information lag or decision-making errors. Through the adjustment suggestions fed back by the system, farms can flexibly adjust prevention and control measures such as immunization, monitoring and isolation, thereby improving the overall prevention and control effect.

[0135] Example 2

[0136] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes an environmental data acquisition unit, a cattle and sheep health data acquisition unit, and a human and logistics data acquisition unit;

[0137] The environmental data acquisition unit collects environmental parameters related to the spread of brucellosis, including temperature T, humidity H and air circulation rate F; the temperature T and humidity H are obtained by temperature sensors and humidity sensors installed in the farm, and the air circulation rate F is obtained by wind speed sensors;

[0138] The cattle and sheep health data collection unit collects cattle and sheep health data, including historical antibody levels Ah and abortion rates Lr; the historical antibody levels Ah are obtained by regularly collecting cattle and sheep serum samples every month and testing them in the laboratory; the abortion rate Lr is automatically calculated and obtained by recording the frequency of abortion events in cattle and sheep in the past year through the management system;

[0139] The abortion rate Lr is obtained by the ratio of the number of aborted individuals in one year to the total number of pregnant individuals in the group;

[0140] The personnel and logistics data collection unit monitors data related to outside personnel and logistics, including the personnel contact frequency Cp and the number of outside cattle and sheep In; the personnel contact frequency Cp is obtained through the access control system and the electronic sign-in record; the number of outside cattle and sheep In is obtained by recording the number of cattle and sheep transferred into the farm, and the environmental parameters, cattle and sheep health data and personnel and logistics data are summarized and fitted into a data pool X.

[0141] The data processing module includes a data standardization unit and a core indicator calculation unit;

[0142] The standardization unit normalizes the data in the data pool X to eliminate the influence of different parameter dimensions and obtains the data set W;

[0143] The data set W is obtained by the following formula:

[0144]

[0145] Where Wi represents the data value of the i-th item in the data set W, Xi represents the data value of the i-th item in the data pool X, Xi,min represents the valley value of the data value of the i-th item in the data pool X, and Xi,max represents the peak value of the data value of the i-th item in the data pool X;

[0146] The core indicator calculation unit calculates the core indicators based on the standardized data set W, including the environmental risk score Re, the cattle and sheep health score Hs, and the human flow and logistics risk score Cr;

[0147] The environmental risk score Re is obtained by the following formula:

[0148]

[0149] In the formula, ln represents the natural logarithm function;

[0150] The cattle and sheep health score Hs is obtained by the following formula:

[0151]

[0152] Where e -Ah represents the exponential decay effect of antibody levels;

[0153] The personnel and logistics risk score Cr is obtained by the following formula:

[0154]

[0155] In the formula, ln represents the natural logarithm function

[0156] In this embodiment, the data acquisition module can record in detail the farm environmental data closely related to the spread of brucellosis through real-time collection of environmental parameters such as temperature, humidity, and air circulation rate. Through the use of high-precision sensors including temperature sensors, humidity sensors, and wind speed sensors, the accuracy and timeliness of environmental data are ensured, providing a reliable basis for subsequent risk assessment and prediction. The cattle and sheep health data acquisition unit can comprehensively reflect the health status of cattle and sheep groups by regularly collecting serum samples and analyzing historical antibody levels, calculating abortion rates, etc. Monitoring of historical antibody levels and abortion rates helps to detect group health problems and potential brucellosis risks at an early stage, especially in the process of immune effect evaluation and disease transmission, and can provide strong data support for subsequent prevention and control decisions.

[0157] The human and logistics data collection unit effectively tracks the frequency of human contact and the number of foreign cattle and sheep through access control systems, electronic sign-in records, and monitoring of the number of cattle and sheep transferred into the farm, and can evaluate the impact of external risks on the spread of brucellosis in real time. This module helps identify potential sources of infection introduced by external personnel or cattle and sheep, and take timely prevention and control measures to reduce the possibility of epidemic spread. The data processing module normalizes the environment, cattle and sheep health, and human and logistics data through standardization units to eliminate the impact of different parameter dimensions.

[0158] By calculating environmental risk scores, cattle and sheep health scores, and human and logistics risk scores, the system can dynamically assess the risk of brucellosis transmission and, combined with real-time data, issue early warning signals in a timely manner. The advantage of this system is that it can flexibly adjust prevention and control measures based on real-time changing multi-factor data, avoiding the lag in traditional brucellosis prevention and control methods and providing more timely and intelligent prevention methods.

[0159] Example 3

[0160] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the AI ​​risk prediction module includes a data input and preprocessing unit and a risk prediction and output unit;

[0161] The data input and preprocessing unit performs feature combination and normalization processing on the received environmental risk score Re, cattle and sheep health score Hs and human flow and logistics risk score Cr to obtain a feature set Y = {L1, L2, L3};

[0162] In the formula, L1 represents the relative impact of comprehensive assessment of environmental risk and health status; L2 represents the weighted cumulative effect of core indicators; L3 represents the square accumulation of environmental and health scores;

[0163] The relative impact L1 of the comprehensive assessment of environmental risks and health conditions is obtained by the following formula:

[0164]

[0165] The weighted cumulative effect L2 of the core indicators is obtained by the following formula:

[0166] L2=ln(1+Re+Hs+Cr);

[0167] In the formula, ln represents the natural logarithm function;

[0168] The square accumulation L3 of the environmental and health scores is obtained by the following formula:

[0169]

[0170] The relative impact L1 of the comprehensive assessment of environmental risks and health conditions, the weighted cumulative effect L2 of the core indicators and the square accumulation L3 of the environmental and health scores were normalized to obtain the feature set Y = {L1, L2, L3}.

[0171] The risk prediction and output unit trains and predicts the input feature set Y by using a three-layer neural network model, and outputs the brucellosis infection risk probability Pr and the corresponding risk level;

[0172] The brucellosis infection risk probability Pr is obtained through the first output layer Z1 and the second output layer Z2 of the three-layer neural network model; the first output layer Z1 and the second output layer Z2 are obtained through the following formula:

[0173] Z1=σ(V1*Y+b1);

[0174] Z2=σ(V2*Z1+b2);

[0175] Where σ represents the Sigmoid activation function, b1 and b2 represent bias vectors, and V1 and V2 represent weight matrices;

[0176] The brucellosis infection risk probability Pr is obtained by the following formula:

[0177] Pr=σ(V3*Z2+b3);

[0178] Where b3 represents the bias vector and V3 represents the weight matrix;

[0179] According to the obtained brucellosis infection risk probability Pr, the corresponding risk level is divided;

[0180] The risk level is obtained by matching:

[0181] When the brucellosis infection risk probability Pr is less than 0.3, it is marked as the first risk level and monitored normally;

[0182] When 0.3≤brucellosis infection risk probability Pr≤0.7, it is marked as the second risk level and is monitored intensively;

[0183] When the brucellosis infection risk probability Pr>0.7, it is marked as the third risk level and control measures are taken.

[0184] In this embodiment, the AI ​​risk prediction module combines and normalizes the environmental risk score, cattle and sheep health score, and human and logistics risk score through data input and preprocessing units to generate a feature set Y. By combining multiple important risk factors and standardizing them, it is ensured that the assessment of brucellosis infection risk can fully and accurately reflect the actual situation of the farm. This multi-dimensional comprehensive assessment method can capture complex disease transmission patterns better than a single risk assessment, and improves the accuracy of the prediction results. By introducing a three-layer neural network model to train and predict the feature set Y, the system can automatically adjust and optimize the prediction model based on various types of data collected in real time. This deep learning model can continuously learn from historical data and real-time input, improving the accuracy and response speed of brucellosis infection risk prediction.

[0185] The probability of brucellosis infection risk Pr is calculated through the output of the three-layer neural network model combined with the Sigmoid activation function to obtain the infection risk probability value. This probability value not only makes the assessment of brucellosis infection risk more refined, but also provides a probability-based risk level division, helping managers to understand the current risk level more clearly and facilitate the adoption of targeted prevention and control measures. The output of the probability value avoids the unclear qualitative nature of traditional assessment methods and improves the scientificity and reliability of decision-making. According to the value of the probability of brucellosis infection risk Pr, the system divides it into different risk levels and provides corresponding management suggestions. When the risk probability is low, the system automatically adjusts to normal monitoring; when the risk probability is medium, the system reminds managers to strengthen monitoring; when the risk probability is high, the system recommends taking control measures immediately. This automated hierarchical management helps farm managers efficiently respond to different risk levels, reduce the delay of manual decision-making, and improve response speed and accuracy.

[0186] Example 4

[0187] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the monitoring and investigation module includes an action plan generation unit and an antibody level detection unit;

[0188] The action plan generating unit generates an action plan according to the brucellosis infection risk probability Pr and the risk level, including a screening range NS, a detection frequency FD and an isolation strategy NI;

[0189] The screening range NS is obtained by the following formula:

[0190] NS = Pr * Nt;

[0191] In the formula, Nt represents the total number of cattle and sheep in the farm;

[0192] The detection frequency FD is obtained by the following formula:

[0193]

[0194] The isolation strategy NI is obtained by the following formula:

[0195]

[0196] In the formula, Ir represents the proportion of positive individuals found in the test, and Dr represents the detection accuracy error coefficient.

[0197] The antibody level detection unit collects blood samples from the screened individuals, detects the average antibody level Am and the antibody qualification rate Ra, obtains the individual antibody level AQ, and compares it with the preset immune threshold Ta to determine the immune status of the cattle and sheep individuals:

[0198] The average antibody level Am is obtained by the following formula:

[0199]

[0200] In the formula, ATi represents the antibody value of the i-th cattle and sheep, and n represents the total number of tested individuals;

[0201] The antibody qualified rate Ra is obtained by the ratio of the number of individuals with antibody levels higher than the average antibody level Am to the total number of tested individuals n;

[0202] The individual antibody level AQ is obtained by the following formula:

[0203]

[0204] In the formula, Na represents the number of individuals with qualified antibodies, and ln represents the natural logarithm function;

[0205] The immune status of the cattle and sheep individuals is obtained by matching in the following manner:

[0206] When the individual antibody level AQ is less than the immune threshold Ta, it means that the individual antibody level does not meet the standard and is listed as a key observation object;

[0207] When the individual antibody level AQ ≥ the immune threshold Ta, it means that the individual antibody level has reached the standard and continues to be monitored.

[0208] In this embodiment, the monitoring and investigation module generates a specific action plan based on the brucellosis infection risk probability Pr and the risk level, covering aspects such as screening scope, detection frequency and isolation strategy. This action plan based on real-time risk prediction enables the prevention and control measures of the farm to accurately match the current epidemic risk level, ensuring that each step of the prevention and control action is targeted and efficient. By dynamically adjusting the screening range and detection frequency, the traditional "one-size-fits-all" monitoring is avoided and the efficiency of resource use is improved. By dynamically calculating the screening range NS and the detection frequency FD, the system can adjust the key areas and frequency of prevention and control according to the size of the infection risk. When the risk is high, expand the screening range and increase the detection frequency; in low-risk situations, appropriately narrow the screening range and reduce the detection frequency. This mechanism avoids waste of resources, while improving the flexibility and effectiveness of prevention and control measures, ensuring that brucellosis infection can be discovered and responded to in a timely manner at an early stage.

[0209] The isolation strategy NI is calculated based on the proportion of positive individuals found in the test Ir and the test accuracy error coefficient Dr, so as to formulate a suitable isolation strategy. This method reduces the number of mis-isolations through accurate individual identification and isolation decisions, while ensuring that positive individuals can be isolated and treated in a timely manner, thereby effectively preventing the spread of brucellosis. By combining infection risk and detection accuracy, this strategy improves the consistency and accuracy of prevention and control work.

[0210] The antibody level detection unit collects individual blood samples and detects their antibody levels, and combines the immune threshold Ta to intelligently determine the individual's immune status. By calculating the individual antibody level AQ, the system can clearly distinguish between individuals who meet the immune standard and those who do not. For individuals who do not meet the immune standard, they will be listed as key observation objects for follow-up tracking and intervention to avoid the spread of the epidemic due to insufficient immune effect. This accurate immune status assessment ensures the targeted nature of immune work and improves the effectiveness of brucellosis prevention and control.

[0211] By continuously monitoring and accurately evaluating the effects of immunization, the system can improve immunization coverage and ensure that individuals infected with wild brucellosis and potential sources of transmission are promptly identified and isolated. By optimizing immunization strategies and accurate screening mechanisms, the risk of brucellosis transmission in cattle and sheep populations can be further reduced. Through accurate evaluation of individual antibody levels and real-time correction of immunization strategies, the system can ensure continuous optimization of immunization measures, maximize immunization effects, and reduce omissions or excessive interventions in immunization work, thereby maximizing brucellosis prevention and control goals.

[0212] Example 5

[0213] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the immune effect evaluation module includes an immune evaluation unit and an immune strategy correction unit;

[0214] The immune assessment unit obtains the population antibody mean deviation value ΔAm based on the average antibody level Am, and determines the immune effect:

[0215] The population antibody mean deviation ΔAm is obtained by the following formula:

[0216] ΔAm=Am-Ta;

[0217] The immune effect is obtained by:

[0218] When the population antibody mean deviation value ΔAm>0, it means that the vaccine effect meets expectations;

[0219] When the population antibody mean deviation ΔAm is less than 0, it means that the vaccine effect does not meet expectations and the immunization strategy should be revised;

[0220] Through the individual antibody level AQ, the immune coverage rate FRA is obtained and the immune coverage efficiency is judged:

[0221] The immunization coverage rate FRA is obtained by the following formula:

[0222]

[0223] The immune coverage efficiency is obtained by:

[0224] When the immunization coverage rate FRA is less than 85%, it means that the immunization coverage does not meet the standard and there is a blind spot, so the immunization strategy should be revised;

[0225] When the immunization coverage rate FRA ≥ 85%, it means that the immunization coverage has met the standard.

[0226] The immunization strategy revision unit obtains the immunization reinforcement area according to the vaccine effect and the immunization coverage rate FRA, and revises the immunization strategy, including vaccine dosage adjustment and immunization frequency adjustment;

[0227] The immune enhancement area is obtained by:

[0228]

[0229] In the formula, Rf represents the set of individuals that need immune enhancement, and Gi represents the individual immune contribution rate;

[0230] The vaccine dose adjustment formula is as follows:

[0231]

[0232] In the formula, Dv represents the vaccine dose required for booster immunization, and Db represents the basic immunization dose;

[0233] The immunization frequency adjustment formula is as follows:

[0234]

[0235] Wherein, Ra represents the antibody qualification rate.

[0236] The intelligent early warning and feedback module includes a risk early warning unit and an adjustment suggestion generation unit;

[0237] The risk warning unit calculates and obtains the comprehensive immune status score Sc according to the brucellosis infection risk probability Pr and the average antibody level Am;

[0238] The comprehensive immune status score Sc is obtained by the following formula:

[0239]

[0240] The adjustment suggestion generating unit generates a management adjustment suggestion AG according to the comprehensive immune status score Sc;

[0241] The adjustment suggestion AG obtains the following methods:

[0242]

[0243] In this embodiment, the immune effect evaluation module can accurately evaluate the immune effect and immune coverage of the vaccine through the group antibody mean deviation value ΔAm and the immune coverage rate FRA. By real-time monitoring of the group immunity status, the system can issue warnings and correct the immune strategy in time when the vaccine effect is not up to standard or the immune coverage is insufficient. This can ensure that the immunization work of the farm always meets expectations and avoid the spread of brucellosis due to insufficient immunization. The immune strategy correction unit automatically determines the immune reinforcement area, optimizes the vaccine dose and immunization frequency based on the group immunity effect evaluation and immune coverage. By dynamically adjusting the immune measures according to the changes in immune coverage and antibody levels, the immune coverage rate can be effectively improved to ensure the continuous optimization of prevention and control work. The intelligent correction function of this strategy effectively avoids errors caused by human intervention and improves the flexibility and accuracy of the immune strategy.

[0244] The immunization coverage rate FRA is calculated by the individual antibody level AQ to ensure that the immunization coverage reaches the target of more than 85%. When the immunization coverage rate does not meet the target, the system will automatically make correction suggestions and strengthen immunization measures in blind areas. Such precise control helps to timely discover immunization blind spots and avoid the spread of epidemics caused by insufficient immunization. Through the calculation of the comprehensive immunization status score Sc, the system can comprehensively evaluate the current immunization effect and risk level. Combined with the brucellosis infection risk probability Pr and the average antibody level Am, the system can dynamically generate a comprehensive immunization status score, predict potential risks in advance and issue early warnings, and provide managers with a basis for decision-making. This can provide timely feedback and guidance for brucellosis prevention and control work in farms, take intervention measures in advance, and avoid the accumulation and outbreak of risks.

[0245] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A brucellosis prevention and control and intelligent early warning system for cattle and sheep in breeding farms, characterized by: It includes data collection module, data processing module, AI risk prediction module, monitoring and investigation module, immune effect evaluation module and intelligent early warning and feedback module; The data acquisition module collects real-time data and historical data, including environmental parameters, cattle and sheep health data, and human and logistics data, and establishes a data pool X; The data processing module standardizes and classifies the data pool X, and calculates core indicators, including the environmental risk score Re, the cattle and sheep health score Hs, and the human and logistics risk score Cr; The AI ​​risk prediction module predicts the risk of brucellosis infection based on the core indicators by using a three-layer neural network model to obtain the brucellosis infection risk probability Pr and risk level; The monitoring and screening module generates a specific action plan based on the brucellosis infection risk probability Pr and risk level, and detects the average antibody level Am and the antibody qualification rate Ra to obtain the individual antibody level AQ; The immune effect evaluation module evaluates the vaccine effect and immune coverage rate FRA through the individual antibody level AQ and the average antibody level Am, and modifies the immune strategy; The intelligent early warning and feedback module feeds back the brucellosis infection risk probability Pr and the average antibody level Am to the manager and generates adjustment suggestions.

2. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 1, characterized in that: The data collection module includes an environmental data collection unit, a cattle and sheep health data collection unit, and a human and logistics data collection unit; The environmental data acquisition unit collects environmental parameters related to the spread of brucellosis, including temperature T, humidity H and air circulation rate F; the temperature T and humidity H are obtained by temperature sensors and humidity sensors installed in the farm, and the air circulation rate F is obtained by wind speed sensors; The cattle and sheep health data collection unit collects cattle and sheep health data, including historical antibody levels Ah and abortion rates Lr; the historical antibody levels Ah are obtained by regularly collecting cattle and sheep serum samples every month and testing them in the laboratory; the abortion rate Lr is automatically calculated and obtained by recording the frequency of abortion events in cattle and sheep in the past year through the management system; The abortion rate Lr is obtained by the ratio of the number of aborted individuals in one year to the total number of pregnant individuals in the group; The personnel and logistics data collection unit monitors data related to outside personnel and logistics, including the personnel contact frequency Cp and the number of outside cattle and sheep In; the personnel contact frequency Cp is obtained through the access control system and the electronic sign-in record; the number of outside cattle and sheep In is obtained by recording the number of cattle and sheep transferred into the farm, and the environmental parameters, cattle and sheep health data and personnel and logistics data are summarized and fitted into a data pool X.

3. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 1 is characterized by: The data processing module includes a data standardization unit and a core indicator calculation unit; The standardization unit normalizes the data in the data pool X to eliminate the influence of different parameter dimensions and obtains the data set W; The data set W is obtained by the following formula: Where Wi represents the data value of the i-th item in the data set W, Xi represents the data value of the i-th item in the data pool X, Xi,min represents the valley value of the data value of the i-th item in the data pool X, and Xi,max represents the peak value of the data value of the i-th item in the data pool X; The core indicator calculation unit calculates the core indicators based on the standardized data set W, including the environmental risk score Re, the cattle and sheep health score Hs, and the human flow and logistics risk score Cr; The environmental risk score Re is obtained by the following formula: In the formula, ln represents the natural logarithm function; The cattle and sheep health score Hs is obtained by the following formula: Where e -Ah represents the exponential decay effect of antibody levels; The personnel and logistics risk score Cr is obtained by the following formula: Where ln represents the natural logarithm function.

4. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 1 is characterized by: The AI ​​risk prediction module includes a data input and preprocessing unit and a risk prediction and output unit; The data input and preprocessing unit performs feature combination and normalization processing on the received environmental risk score Re, cattle and sheep health score Hs and human flow and logistics risk score Cr to obtain a feature set Y = {L1, L2, L3}; In the formula, L1 represents the relative impact of comprehensive assessment of environmental risk and health status; L2 represents the weighted cumulative effect of core indicators; L3 represents the square accumulation of environmental and health scores; The relative impact L1 of the comprehensive assessment of environmental risks and health conditions is obtained by the following formula: The weighted cumulative effect L2 of the core indicators is obtained by the following formula: L2=ln(1+Re+Hs+Cr); In the formula, ln represents the natural logarithm function; The square accumulation L3 of the environmental and health scores is obtained by the following formula: The relative impact L1 of the comprehensive assessment of environmental risks and health conditions, the weighted cumulative effect L2 of the core indicators and the square accumulation L3 of the environmental and health scores were normalized to obtain the feature set Y = {L1, L2, L3}.

5. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 4 is characterized by: The risk prediction and output unit trains and predicts the input feature set Y by using a three-layer neural network model, and outputs the brucellosis infection risk probability Pr and the corresponding risk level; The brucellosis infection risk probability Pr is obtained through the first output layer Z1 and the second output layer Z2 of the three-layer neural network model; The first output layer Z1 and the second output layer Z2 are obtained by the following formula: Z1=σ(V1*Y+b1); Z2=σ(V2*Z1+b2); Where σ represents the Sigmoid activation function, b1 and b2 represent bias vectors, and V1 and V2 represent weight matrices; The brucellosis infection risk probability Pr is obtained by the following formula: Pr=σ(V3*Z2+b3); Where b3 represents the bias vector and V3 represents the weight matrix; According to the obtained brucellosis infection risk probability Pr, the corresponding risk level is divided; The risk level is obtained by matching: When the brucellosis infection risk probability Pr is less than 0.3, it is marked as the first risk level and monitored normally; When 0.3≤brucellosis infection risk probability Pr≤0.7, it is marked as the second risk level and is monitored intensively; When the brucellosis infection risk probability Pr>0.7, it is marked as the third risk level and control measures are taken.

6. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 5, characterized in that: The monitoring and troubleshooting module includes an action plan generation unit and an antibody level detection unit; The action plan generating unit generates an action plan according to the brucellosis infection risk probability Pr and the risk level, including a screening range NS, a detection frequency FD and an isolation strategy NI; The screening range NS is obtained by the following formula: NS = Pr * Nt; In the formula, Nt represents the total number of cattle and sheep in the farm; The detection frequency FD is obtained by the following formula: The isolation strategy NI is obtained by the following formula: In the formula, Ir represents the proportion of positive individuals found in the test, and Dr represents the detection accuracy error coefficient.

7. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 6, characterized in that: The antibody level detection unit collects blood samples from the screened individuals, detects the average antibody level Am and the antibody qualification rate Ra, obtains the individual antibody level AQ, and compares it with the preset immune threshold Ta to determine the immune status of the cattle and sheep individuals: The average antibody level Am is obtained by the following formula: In the formula, ATi represents the antibody value of the i-th cattle and sheep, and n represents the total number of tested individuals; The antibody qualified rate Ra is obtained by the ratio of the number of individuals whose antibody levels are higher than the average antibody level Am to the total number of tested individuals n; The individual antibody level AQ is obtained by the following formula: In the formula, Na represents the number of individuals with qualified antibodies, and ln represents the natural logarithm function; The immune status of the cattle and sheep individuals is obtained by matching in the following manner: When the individual antibody level AQ is less than the immune threshold Ta, it means that the individual antibody level does not meet the standard and is listed as a key observation object; When the individual antibody level AQ ≥ the immune threshold Ta, it means that the individual antibody level has reached the standard and monitoring should continue.

8. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 7, characterized in that: The immune effect evaluation module includes an immune evaluation unit and an immune strategy correction unit; The immune assessment unit obtains the population antibody mean deviation value ΔAm based on the average antibody level Am, and determines the immune effect: The population antibody mean deviation ΔAm is obtained by the following formula: ΔAm=Am-Ta; The immune effect is obtained by: When the population antibody mean deviation value ΔAm>0, it means that the vaccine effect meets expectations; When the population antibody mean deviation ΔAm is less than 0, it means that the vaccine effect does not meet expectations and the immunization strategy should be revised; Through the individual antibody level AQ, the immune coverage rate FRA is obtained and the immune coverage efficiency is judged: The immunization coverage rate FRA is obtained by the following formula: The immune coverage efficiency is obtained by: When the immunization coverage rate FRA is less than 85%, it means that the immunization coverage does not meet the standard and there is a blind spot, so the immunization strategy should be revised; When the immunization coverage rate FRA ≥ 85%, it means that the immunization coverage has met the standard.

9. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 8, characterized in that: The immunization strategy revision unit obtains the immunization reinforcement area according to the vaccine effect and the immunization coverage rate FRA, and revises the immunization strategy, including vaccine dosage adjustment and immunization frequency adjustment; The immune enhancement area is obtained by: In the formula, Rf represents the set of individuals that need immune enhancement, and Gi represents the individual immune contribution rate; The vaccine dose adjustment formula is as follows: In the formula, Dv represents the vaccine dose required for booster immunization, and Db represents the basic immunization dose; The immunization frequency adjustment formula is as follows: Wherein, Ra represents the antibody qualification rate.

10. The brucellosis prevention and control and intelligent early warning system for cattle and sheep in a breeding farm according to claim 1, characterized in that: The intelligent early warning and feedback module includes a risk early warning unit and an adjustment suggestion generation unit; The risk warning unit calculates and obtains the comprehensive immune status score Sc according to the brucellosis infection risk probability Pr and the average antibody level Am; The comprehensive immune status score Sc is obtained by the following formula: The adjustment suggestion generating unit generates a management adjustment suggestion AG according to the comprehensive immune status score Sc; The adjustment suggestion AG obtains the following methods:

Images